Functions — github.com/PKU-MARL/HARL

CodeHub MCPcopy Create free account

hub / github.com/PKU-MARL/HARL / functions

Functions1,457 in github.com/PKU-MARL/HARL

⨍ Functions 1,457◇ Types & classes 185

( self, cfg, sim_params, physics_engine, device_type, device_i

harl/envs/dexhands/DexterousHands/bidexhands/tasks/shadow_hand_lift_underarm.py:62

( self, cfg, sim_params, physics_engine, device_type, device_i

harl/envs/dexhands/DexterousHands/bidexhands/tasks/shadow_hand_door_open_inward.py:63

( self, cfg, sim_params, physics_engine, device_type, device_i

harl/envs/dexhands/DexterousHands/bidexhands/tasks/shadow_hand_point_cloud.py:48

( self, cfg, sim_params, physics_engine, device_type, device_i

harl/envs/dexhands/DexterousHands/bidexhands/tasks/shadow_hand_catch_underarm.py:62

(self, task, rl_device, clip_observations=5.0, clip_actions=1.0)

harl/envs/dexhands/DexterousHands/bidexhands/tasks/hand_base/multi_vec_task.py:25

( self, task: BaseTask, rl_device, clip_observations=5.0, clip_actions=1.0 )

harl/envs/dexhands/DexterousHands/bidexhands/tasks/hand_base/multi_vec_task.py:278

( self, task, rl_device, sync_frame_time=False, clip_observations=5.0,

harl/envs/dexhands/DexterousHands/bidexhands/tasks/hand_base/vec_task_rlgames.py:115

(self, task, rl_device, clip_observations=5.0, clip_actions=1.0)

harl/envs/dexhands/DexterousHands/bidexhands/tasks/hand_base/vec_task_rlgames.py:167

(self, task, rl_device, clip_observations=5.0, clip_actions=1.0)

harl/envs/dexhands/DexterousHands/bidexhands/tasks/hand_base/meta_vec_task.py:19

( self, task, rl_device, sync_frame_time=False, clip_observations=5.0,

harl/envs/dexhands/DexterousHands/bidexhands/tasks/hand_base/vec_task.py:75

(self, task, rl_device, clip_observations=5.0, clip_actions=1.0)

harl/envs/dexhands/DexterousHands/bidexhands/tasks/hand_base/vec_task.py:127

(self, task, rl_device, clip_observations=5.0, clip_actions=1.0)

harl/envs/dexhands/DexterousHands/bidexhands/tasks/hand_base/multi_task_vec_task.py:19

(self, cfg, enable_camera_sensors=False, is_meta=False, task_num=0)

harl/envs/dexhands/DexterousHands/bidexhands/tasks/hand_base/base_task.py:30

( self, cfg, sim_params, physics_engine, device_type, device_i

harl/envs/dexhands/DexterousHands/bidexhands/tasks/shadow_hand_meta/shadow_hand_meta_mt1.py:26

( self, cfg, sim_params, physics_engine, device_type, device_i

harl/envs/dexhands/DexterousHands/bidexhands/tasks/shadow_hand_meta/shadow_hand_meta_mt4.py:25

( self, cfg, sim_params, physics_engine, device_type, device_i

harl/envs/dexhands/DexterousHands/bidexhands/tasks/shadow_hand_meta/shadow_hand_meta_ml1.py:26

(self, args, algo_args, env_args, num_agents, writter, run_dir)

harl/envs/smac/smac_logger.py:8

Create a StarCraftC2Env environment. Parameters ---------- map_name : str, optional The name of the SC2

harl/envs/smac/StarCraft2_Env.py:72

harl/envs/pettingzoo_mpe/pettingzoo_mpe_env.py:12

harl/envs/football/football_env.py:18

(self, env_args)

harl/envs/lag/lag_env.py:12

harl/envs/lag/JSBSim/reward_functions/missile_posture_reward.py:10

harl/envs/lag/JSBSim/reward_functions/shoot_penalty_reward.py:10

harl/envs/lag/JSBSim/reward_functions/event_driven_reward.py:12

harl/envs/lag/JSBSim/reward_functions/posture_reward.py:16

harl/envs/lag/JSBSim/reward_functions/reward_function_base.py:11

harl/envs/lag/JSBSim/reward_functions/relative_altitude_reward.py:14

harl/envs/lag/JSBSim/reward_functions/heading_reward.py:10

harl/envs/lag/JSBSim/reward_functions/altitude_reward.py:12

harl/envs/lag/JSBSim/core/render_tacview.py:20

Constructor. Creates an instance of JSBSim, loads an aircraft and sets initial conditions. Args: uid (str): 5-digits hexadecimal

harl/envs/lag/JSBSim/core/simulatior.py:98

(self, uid="A0101", color="Red", model="AIM-9L",

harl/envs/lag/JSBSim/core/simulatior.py:344

(self, agent_id)

harl/envs/lag/JSBSim/model/baseline.py:16

(self, agent_id, maneuver: Literal['l', 'r', 'n'])

harl/envs/lag/JSBSim/model/baseline.py:75

(self, input_dim, hidden_size)

harl/envs/lag/JSBSim/model/baseline_actor.py:13

(self, input_size, hidden_size, num_layers)

harl/envs/lag/JSBSim/model/baseline_actor.py:42

(self, input_dim, output_dim)

harl/envs/lag/JSBSim/model/baseline_actor.py:60

(self, input_dim, action_dims, use_mlp_actlayer=False)

harl/envs/lag/JSBSim/model/baseline_actor.py:70

(self, input_dim=12, use_mlp_actlayer=False)

harl/envs/lag/JSBSim/model/baseline_actor.py:92

(self, agent_id)

harl/envs/lag/JSBSim/test/test_baseline_use_env.py:18

(self, agent_id, maneuver: Literal['l', 'r', 'n'])

harl/envs/lag/JSBSim/test/test_baseline_use_env.py:99

(self, agent_id)

harl/envs/lag/JSBSim/test/test_baseline_use_obs.py:16

(self, agent_id, maneuver: Literal['l', 'r', 'n'])

harl/envs/lag/JSBSim/test/test_baseline_use_obs.py:75

(self, config_name: str)

harl/envs/lag/JSBSim/envs/env_base.py:22

(self, config_name: str)

harl/envs/lag/JSBSim/envs/singlecombat_env.py:11

(self, config_name: str)

harl/envs/lag/JSBSim/envs/multiplecombat_env.py:11

(self, config_name: str)

harl/envs/lag/JSBSim/envs/singlecontrol_env.py:9

harl/envs/lag/JSBSim/termination_conditions/overload.py:12

harl/envs/lag/JSBSim/termination_conditions/termination_condition_base.py:11

harl/envs/lag/JSBSim/termination_conditions/extreme_state.py:11

harl/envs/lag/JSBSim/termination_conditions/safe_return.py:12

harl/envs/lag/JSBSim/termination_conditions/timeout.py:10

harl/envs/lag/JSBSim/termination_conditions/unreach_heading.py:12

harl/envs/lag/JSBSim/termination_conditions/low_altitude.py:11

(self, config: str)

harl/envs/lag/JSBSim/tasks/multiplecombat_task.py:136

(self, config: str)

harl/envs/lag/JSBSim/tasks/multiplecombat_task.py:182

(self, config: str)

harl/envs/lag/JSBSim/tasks/multiplecombat_vs_baseline_task.py:98

harl/envs/lag/JSBSim/tasks/singlecombat_task.py:15

(self, config: str)

harl/envs/lag/JSBSim/tasks/singlecombat_task.py:204

harl/envs/lag/JSBSim/tasks/singlecombat_task.py:271

(self, maneuver: Literal['l', 'r', 'n'])

harl/envs/lag/JSBSim/tasks/singlecombat_task.py:356

harl/envs/lag/JSBSim/tasks/singlecombat_task.py:398

(self, config: str)

harl/envs/lag/JSBSim/tasks/singlecombat_with_missle_task.py:131

harl/envs/lag/JSBSim/tasks/singlecombat_with_missle_task.py:162

(self, config: str)

harl/envs/lag/JSBSim/tasks/singlecombat_with_missle_task.py:204

harl/envs/lag/JSBSim/tasks/task_base.py:14

harl/envs/lag/JSBSim/tasks/heading_task.py:13

( self, label, qpos_ids, qvel_ids, act_ids, body_fn=None,

harl/envs/mamujoco/multiagent_mujoco/obsk.py:7

harl/envs/mamujoco/multiagent_mujoco/obsk.py:36

(self, **kwargs)

harl/envs/mamujoco/multiagent_mujoco/manyagent_ant.py:9

(self, **kwargs)

harl/envs/mamujoco/multiagent_mujoco/coupled_half_cheetah.py:8

(self, **kwargs)

harl/envs/mamujoco/multiagent_mujoco/manyagent_swimmer.py:9

(self, batch_size=None, **kwargs)

harl/envs/mamujoco/multiagent_mujoco/mujoco_multi.py:40

(self, batch_size=None, **kwargs)

harl/envs/mamujoco/multiagent_mujoco/multiagentenv.py:10

harl/envs/gym/gym_env.py:6

( self, input_shape, norm_axes=1, beta=0.99999, per_element_update=Fal

harl/common/valuenorm.py:10

Initialize the logger.

harl/common/base_logger.py:13

Initialize on-policy actor buffer. Args: args: (dict) arguments obs_space: (gym.Space or list) observation space

harl/common/buffers/on_policy_actor_buffer.py:12

Initialize off-policy buffer. Args: args: (dict) arguments share_obs_space: (gym.Space or list) share observation spac

harl/common/buffers/off_policy_buffer_base.py:7

Initialize on-policy critic buffer. Args: args: (dict) arguments share_obs_space: (gym.Space or list) share observatio

harl/common/buffers/on_policy_critic_buffer_fp.py:13

Initialize on-policy critic buffer. Args: args: (dict) arguments share_obs_space: (gym.Space or list) share observatio

harl/common/buffers/on_policy_critic_buffer_ep.py:11

Initialize off-policy buffer. Args: args: (dict) arguments share_obs_space: (gym.Space or list) share observation spac

harl/common/buffers/off_policy_buffer_ep.py:10

Initialize off-policy buffer. Args: args: (dict) arguments share_obs_space: (gym.Space or list) share observation spac

harl/common/buffers/off_policy_buffer_fp.py:12

Initialize VNet model. Args: args: (dict) arguments containing relevant model information. cent_obs_space: (gym.Space)

harl/models/value_function_models/v_net.py:13

(self, args, cent_obs_space, act_spaces, device=torch.device("cpu"))

harl/models/value_function_models/continuous_q_net.py:30

(self, args, obs_space, output_dim, device=torch.device("cpu"))

harl/models/value_function_models/dueling_q_net.py:11

Initialize DeterministicPolicy model. Args: args: (dict) arguments containing relevant model information. obs_space: (

harl/models/policy_models/deterministic_policy.py:11

Initialize StochasticMlpPolicy model. Args: args: (dict) arguments containing relevant model information. obs_space: (

harl/models/policy_models/stochastic_mlp_policy.py:12

Initialize StochasticPolicy model. Args: args: (dict) arguments containing relevant model information. obs_space: (gym

harl/models/policy_models/stochastic_policy.py:14

Initialize SquashedGaussianPolicy model. Args: args: (dict) arguments containing relevant model information. obs_space

harl/models/policy_models/squashed_gaussian_policy.py:17

( self, obs_shape, hidden_sizes, initialization_method, activation_fun

harl/models/base/cnn.py:9

( self, obs_shape, hidden_size, activation_func, kernel_size=3, stride=1 )

harl/models/base/plain_cnn.py:9

(self, sizes, activation_func, final_activation_func="identity")

harl/models/base/plain_mlp.py:8

Initialize the MLP layer. Args: input_dim: (int) input dimension. hidden_sizes: (list) list of hidden layer sizes.

harl/models/base/mlp.py:8

(self, inputs_dim, outputs_dim, recurrent_n, initialization_method)

harl/models/base/rnn.py:9

( self, num_inputs, num_outputs, initialization_method="orthogonal_",

harl/models/base/distributions.py:61

Initialize ACTLayer. Args: action_space: (gym.Space) action space. inputs_dim: (int) dimension of network input.

harl/models/base/act.py:9

(self, args, obs_space, act_space, device=torch.device("cpu"))

harl/algorithms/actors/off_policy_base.py:11

Initialize HAPPO algorithm. Args: args: (dict) arguments. obs_space: (gym.spaces or list) observation space.

harl/algorithms/actors/happo.py:11

(self, args, obs_space, act_space, device=torch.device("cpu"))

harl/algorithms/actors/hasac.py:11

← previous next →801–900 of 1,457, ranked by callers